© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15977
    Prev
    Next
    INDEX
    Explanations

    economic activity metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    k
    -1.41
    f
    -1.26
     venne
    -1.18
    ήσει
    -1.16
     '${
    -1.12
    j
    -1.09
    g
    -1.08
    w
    -1.08
    何度
    -1.07
    APOLIS
    -1.07
    POSITIVE LOGITS
     between
    1.79
     in
    1.71
     from
    1.55
     during
    1.37
     estrena
    1.27
    我了
    1.25
     patterns
    1.21
     across
    1.20
    があるので
    1.20
    えもん
    1.20
    Activations Density 0.073%

    No Known Activations